vllm/tests/entrypoints/speech_to_text at main - vllm

obscura/vllm

Fork 0

mirror of https://github.com/vllm-project/vllm.git synced 2026-08-22 21:50:15 +00:00

Files

T

History

1ab2801dde [ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907 )

Signed-off-by: Andreas Karatzas <[email protected]>
Signed-off-by: Andreas Karatzas <[email protected]>
Co-authored-by: OpenAI Codex <[email protected]>

2026-08-11 14:19:16 -04:00

correctness

[CI] Fix speech correctness check rejecting improved WER (#49853 )

2026-07-26 06:24:07 +00:00

realtime

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907 )

2026-08-11 14:19:16 -04:00

transcription

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907 )

2026-08-11 14:19:16 -04:00

translation

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907 )

2026-08-11 14:19:16 -04:00

__init__.py

[CI] Consolidate Speech to Text tests (#42274 )

2026-05-11 19:50:17 +00:00

conftest.py

[ROCm] Remove stale SDPA and skinny GEMM workarounds (#50907 )

2026-08-11 14:19:16 -04:00

test_speech_to_text_cancellation.py

[Bugfix] Changed speech to text chunk timestamp to cumulative approach (#41131 )

2026-07-27 17:06:46 +00:00

test_upload_size_limit.py

(security) Enforce audio upload size limit before full file materialization (#45510 )

2026-06-15 10:25:24 +00:00